#include <gpu_wavenet.hpp>
◆ completion_policy
Selects how the non-realtime service thread waits for completions.
The default preserves the existing ProcessEvents behavior.
◆ completion_wait_ns
| std::uint64_t pulp::gpu_audio::GpuWaveNetSession::Config::completion_wait_ns = 0 |
TimedWaitAny wait budget in nanoseconds.
Zero selects the provider default. This is a dispatcher wait budget, not an audio deadline.
◆ descriptor
◆ slots
| std::uint32_t pulp::gpu_audio::GpuWaveNetSession::Config::slots = 2 |
◆ weights
| std::span<const float> pulp::gpu_audio::GpuWaveNetSession::Config::weights {} |
The documentation for this struct was generated from the following file:
- /home/runner/work/pulp/pulp/core/gpu_audio/include/pulp/gpu_audio/gpu_wavenet.hpp